Detection & Response
Detect risky agent behavior and respond in real time.
AI detection & response
Ggeneral-analysisAIDR
Sensors connectedInteractions18,042+18.6%
Active agents082 unmanaged
Detections032 blocked · 1 held
Interaction volumeLast 24 hours
Claude CodeAgentAIDRInspectingLocal filesConnected
MONITORED SURFACESCoding agentsWorkforce AICustom agentsShadow AI · 2All connected
Recent sessions
Explore a user, agent, or detection to follow the full session.Interactive demo · Illustrative data
Platform
Security tooling built on our research.
Posture Audit
Check configurations against NIST AI RMF, OWASP, and your own policies.
Red Teaming
Run adversarial attacks against your agents.
Remediation
Re-run the attacks against each fix and track the attack success rate.
Runtime Guardrails
Enforce policies on inputs, outputs, and tool calls in production.
Illustrative data
Latest news and research
General Analysis raises $10M to build the security arsenal for the agentic era
Led by Altos Ventures, with 645 Ventures and Menlo Ventures participating, the round funds an empirical security platform pairing adversarial simulation with production defenses.
Guardrail Release
Open-source release of the GA Guard series, a family of safety classifiers that have been providing comprehensive protection for enterprise AI deployments for the past year.
Claude jailbroken to issue a $50,000 Stripe coupon
General AnalysisClaude Jailbroken to Mint Unlimited Stripe Coupons
We reveal a powerful metadata-spoofing attack that exploits Claude's iMessage integration to mint unlimited Stripe coupons or invoke any MCP tool with arbitrary parameters, without alerting the user.
Supabase MCP can leak your private SQL tables
General AnalysisSupabase MCP can leak your entire SQL database
Indirect prompt injection through support-ticket data lets an MCP-enabled assistant cross trust boundaries and query private tables with Supabase’s privileged service role.
The Redact & Recover jailbreak
General AnalysisExploiting Partial Compliance: The Redact-and-Recover Jailbreak
We present the Redact & Recover (RnR) Jailbreak, a novel attack that exploits partial compliance behaviors in frontier LLMs to bypass safety guardrails through a two-phase decomposition strategy.
